AI Paper Atlas

Research map / Detection and segmentation / CNN features

EAFormer: Scene Text Segmentation with Edge-Aware Transformers

Haiyang Yu, Teng Fu, Bin Li, Xiangyang Xue

ECCV 2024 · Detection and segmentation › CNN features · approach: Arbitrary-shape scene text detection · 9 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add edge filtering (remove non-text edges) to SegFormer (ablation)SegFormer · TextSegfgIoU: 84.59 -> 86.85Improved
add edge guidance without edge filtering (ablation)SegFormer · TextSegfgIoU: 84.59 -> 81.03Hurt
add edge guidance on top of edge filtering (ablation)EAFormer · TextSegfgIoU: 86.85 -> 88.06Improved
add edge filtering and guidance on BTS (ablation)SegFormer · BTSfgIoU: 84.99 -> 88.08Improved
use loss weight lambda 1.0 instead of 0.1 (ablation)EAFormer · TextSegfgIoU: 84.03 -> 88.06Improved
vary lambda from 0.5 to 10.0 (ablation)EAFormer · TextSegfgIoU: 87.33 to 88.06No clear effect
introduce edge guidance at third or fourth stage instead of first (ablation)EAFormer · TextSegfgIoUHurt
replace lightweight text detector with pre-trained DBNet (ablation)EAFormer · TextSegfgIoU: 88.06 -> 90.16Improved
train and test on re-annotated COCO_TSEAFormer vs TextFormer · COCO_TS (re-annotated)fgIoU: 52.73 -> 64.82Improved
add text detection head and edge modules to SegFormerEAFormer vs TextFormer · inference costparameters: 85M -> 92M parameters, 0.42s -> 0.47s per imageMixed

Later papers that compared with this method

2 later accepted papers report EAFormer as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy